MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122713 A) filed by S R University, Warangal, Telangana, on Dec. 5, 2025, for 'explainable multi-view mri-based brain tumor classification using deep neural networks.'
Inventor(s) include Naga Maha Lakshmi K; and Durgesh Nandan.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present invention describes a method and system for automatic classification of brain tumors using multi-view magnetic resonance imaging (MRI) scans. The system uses a dual-stream convolutional neural network (CNN), where one branch processes axial slices and the other processes coronal slices. Features from both branches are combined in an attention-guided fusion module that is supervised with radiologist-marked regions of interest (ROIs), so the model learns to focus on important tumor areas. The invention also produces attention heatmaps that highlight the regions influencing the classification, giving doctors a clear explanation of the result. Training uses a combined loss function that balances accuracy with attention supervision, ensuring the model is both reliable and interpretable. The system outputs tumor subtype predictions together with visual explanations, making it useful for diagnosis, treatment planning, and research in neuro-oncology."
Disclaimer: Curated by HT Syndication.
